{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:U6BDALDFZ7JKNI42OOCBDSPBLV","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"39a23215e5c3aae5668160c760c3ebc31f407d18e716022c72aebb54c1a2dfba","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-03-25T04:07:44Z","title_canon_sha256":"7f21195b309d87e58a2dc5029eda1593e1decaf6bf584ae0e37d0c549a499192"},"schema_version":"1.0","source":{"id":"2103.13597","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.13597","created_at":"2026-07-05T02:26:20Z"},{"alias_kind":"arxiv_version","alias_value":"2103.13597v1","created_at":"2026-07-05T02:26:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.13597","created_at":"2026-07-05T02:26:20Z"},{"alias_kind":"pith_short_12","alias_value":"U6BDALDFZ7JK","created_at":"2026-07-05T02:26:20Z"},{"alias_kind":"pith_short_16","alias_value":"U6BDALDFZ7JKNI42","created_at":"2026-07-05T02:26:20Z"},{"alias_kind":"pith_short_8","alias_value":"U6BDALDF","created_at":"2026-07-05T02:26:20Z"}],"graph_snapshots":[{"event_id":"sha256:6b57f7b2f5d6457a5a942f3a6eed9e442d321f973854dd9bf5855347ce847f5f","target":"graph","created_at":"2026-07-05T02:26:20Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2103.13597/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Transformer is an attention-based neural network, which consists of two sublayers, namely, Self-Attention Network (SAN) and Feed-Forward Network (FFN). Existing research explores to enhance the two sublayers separately to improve the capability of Transformer for text representation. In this paper, we present a novel understanding of SAN and FFN as Mask Attention Networks (MANs) and show that they are two special cases of MANs with static mask matrices. However, their static mask matrices limit the capability for localness modeling in text representation learning. We therefore introduce a new ","authors_text":"Dayiheng Liu, Jian Jiao, Nan Duan, Ruofei Zhang, Siyuan Wang, Xuanjing Huang, Yeyun Gong, Zhihao Fan, Zhongyu Wei","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-03-25T04:07:44Z","title":"Mask Attention Networks: Rethinking and Strengthen Transformer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.13597","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:8016cc6c62b9ec727ebaa5f4569615703db304f9d6810741124259473aaddde9","target":"record","created_at":"2026-07-05T02:26:20Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"39a23215e5c3aae5668160c760c3ebc31f407d18e716022c72aebb54c1a2dfba","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-03-25T04:07:44Z","title_canon_sha256":"7f21195b309d87e58a2dc5029eda1593e1decaf6bf584ae0e37d0c549a499192"},"schema_version":"1.0","source":{"id":"2103.13597","kind":"arxiv","version":1}},"canonical_sha256":"a782302c65cfd2a6a39a738411c9e15d7304a0c51ea98d55a799f99767505f16","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a782302c65cfd2a6a39a738411c9e15d7304a0c51ea98d55a799f99767505f16","first_computed_at":"2026-07-05T02:26:20.586107Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:26:20.586107Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ip1KRaOOd7bfDqYJiiRPNmNKTFD6fx1EDvVAjKJqgZ517dLH198klCx3dKHHZHI4N5XfRk+jykjR+pW6lXxfCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:26:20.586538Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.13597","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8016cc6c62b9ec727ebaa5f4569615703db304f9d6810741124259473aaddde9","sha256:6b57f7b2f5d6457a5a942f3a6eed9e442d321f973854dd9bf5855347ce847f5f"],"state_sha256":"70ddfa2055a1279248b098e2652a69f62bfb3619e0ed4c1c29a074a891e1b426"}